© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 1293
    Prev
    Next
    INDEX
    Explanations

    instances of the word "she" and various forms of "he"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enzie
    -0.06
    arium
    -0.06
    cpy
    -0.06
    Dismiss
    -0.06
    alus
    -0.05
    odian
    -0.05
    евÑĸ
    -0.05
     Mos
    -0.05
    ults
    -0.05
    -roll
    -0.05
    POSITIVE LOGITS
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.08
     then
    0.08
    .qq
    0.08
    avaÅŁ
    0.07
    jeta
    0.07
     cũng
    0.07
     also
    0.07
     ayrıca
    0.07
    unca
    0.07
    ota
    0.07
    Activations Density 0.023%

    No Known Activations